What problem does it solve? Writing tests after the fact often produces brittle, implementation-coupled tests that break on every refactor. This Skill enforces a disciplined test-driven development workflow so tests verify real behavior through public interfaces and survive code changes. ## Core Features & Use Cases - Red-Green Loop Discipline: Enforces writing a failing test first, then only the minimal code needed to pass it, one vertical slice at a time. - Seam Identification: Helps you agree on public interface boundaries (seams) before writing any test, focusing effort on critical paths. - Anti-Pattern Detection: Flags implementation-coupled, tautological, and horizontally-sliced tests with concrete good/bad examples in tests.md and mocking guidance in mocking.md. - Use Case: When building a new checkout feature, use this Skill to define the seams with the user, write one failing behavior test like "user can checkout with valid cart", implement just enough code to pass, and repeat. ## Quick Start Ask the AI to build your next feature test-first using the TDD skill, starting by agreeing on the seams to test.